windows-tts
在 Windows 11 上"直接发声"的 TTS(从 WSL2/TUI 调用 powershell.exe + System.Speech)。适用于用户说"说出来/读出来/语音播报/用TTS",或反馈"没声音/tts 生成的 mp3 是空的/播不出来",以及需要中文语音但 OpenClaw 内置 tts 不可用时。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/547895019/windows-tts-wsl2What This Skill Does
The windows-tts skill is a powerful utility designed for OpenClaw users operating within a WSL2 (Windows Subsystem for Linux) environment. It bridges the gap between the Linux subsystem and the Windows host OS by invoking the built-in Windows System.Speech synthesizer via PowerShell. Unlike standard TTS solutions that require complex PulseAudio or WSLg configurations, this skill leverages powershell.exe to trigger audio directly through the default Windows playback device. This ensures a seamless, reliable experience for users who need immediate speech output without wrestling with sound server drivers or virtual audio cables.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/547895019/windows-tts-wsl2
This command automatically fetches the necessary shell scripts (say.sh and list_voices.sh) to your local skill directory, configuring the paths for instant execution.
Use Cases
This skill is specifically engineered for scenarios where audio playback is critical but standard libraries fail. Use it when:
- Your system is configured in WSL2 where local audio drivers (PulseAudio/Pipewire) are improperly mapped or inconsistent.
- You require native, high-quality Windows voice synthesis (Microsoft Speech API).
- You are building a notification agent that needs to "announce" status updates or alerts directly from your desktop.
- OpenClaw's internal TTS engine is producing zero-byte files or is incompatible with your system's output hardware.
Example Prompts
- "OpenClaw, please read out the last error message from the logs using your voice."
- "I can't hear anything when you respond; please try using the windows-tts system for your next output."
- "Hey, use the Chinese voice to read the summary of this article out loud."
Tips & Limitations
- Direct Playback: Note that this skill is a fire-and-forget mechanism; it does not return an audio file path. It is meant for real-time auditory interaction.
- Voice Customization: You can list available system voices using
bash {baseDir}/scripts/list_voices.sh. Once you find a preferred voice, utilize the--voiceflag in thesay.shscript to set a custom persona for your assistant. - Shell Escaping: When calling scripts from bash, be mindful of command injection and character escaping. Use the provided wrapper scripts to avoid PowerShell syntax errors related to variable expansion.
- Dependencies: This skill requires a functional Windows host environment. It is not suitable for bare-metal Linux installations.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-547895019-windows-tts-wsl2": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: code-execution
Related Skills
public-apis-skill-creator
公共API/免费API SKILL生成器:从 public-apis/public-apis 自动检索免费 API,按功能推荐并给出最小可用调用示例(curl/Python/JS),并可自动生成自定义名称的 API skill。用户提到“公共API”“免费API”“public APIs”“找接口/找API”“生成API skill”时触发。
arduino-cli
Provides commands and workflows for Arduino CLI. Use when the user wants to create, compile, or upload Arduino sketches, manage boards (list, attach), install/search/list cores (platforms) and libraries, or configure Arduino CLI. Triggers on phrases like "arduino-cli", "compile sketch", "upload arduino", "install arduino core", or "arduino library".
obsidian-helper
Operate Obsidian vaults from command line. Use when the user wants to list, search, create, read, edit, or delete Obsidian notes, or manage daily notes. Triggers on mentions of "obsidian笔记", "obsidian notes", "obsidian搜索", "obsidian创建", "obsidian列表", or any Obsidian vault operations.
esp-idf-helper
Help develop, build, flash, and debug ESP32/ESP8266 firmware using Espressif ESP-IDF on Linux/WSL. Use when the user asks about ESP-IDF project setup, configuring targets, menuconfig, building, flashing via esptool/idf.py, serial monitor, partition tables, sdkconfig, troubleshooting build/flash/monitor errors, or automating common idf.py workflows from the command line.
qwen-video
Generate videos using Alibaba Cloud DashScope Wan (通义万相) text-to-video (t2v) API (e.g., wan2.6-t2v). Use when the user asks to create a short video from a text prompt via 百炼/通义万相/wan 文生视频, and wants the agent to submit an async task, poll status, and download the mp4 locally (e.g., to Windows Desktop from WSL2).